© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76391
    Prev
    Next
    INDEX
    Explanations

    terms related to security and customer protection in the context of online services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     POLITICO
    -0.08
    onom
    -0.07
    mitter
    -0.06
    лиз
    -0.06
     tumblr
    -0.06
    onta
    -0.06
    hotmail
    -0.06
    ory
    -0.06
    oppins
    -0.06
     leds
    -0.06
    POSITIVE LOGITS
    LOBAL
    0.07
    .Names
    0.07
    irma
    0.06
    zych
    0.06
     integr
    0.06
    lol
    0.06
     handle
    0.06
    earable
    0.06
     ÙĪØ§ÙĦØŃ
    0.05
    稿
    0.05
    Activations Density 0.000%

    No Known Activations